The Role of AI in Characterizing the DCM Phenotype

Artificial Intelligence Advancements in Cardiomyopathies: Implications for Diagnosis and Management of Arrhythmogenic Cardiomyopathy

PURPOSE OF REVIEW

This review aims to explore the emerging potential of artificial intelligence (AI) in refining risk prediction, clinical diagnosis, and treatment stratification for cardiomyopathies, with a specific emphasis on arrhythmogenic cardiomyopathy (ACM).

RECENT FINDINGS

Recent developments highlight the capacity of AI to construct sophisticated models that accurately distinguish affected from non-affected cardiomyopathy patients. These AI-driven approaches not only offer precision in risk prediction and diagnostics but also enable early identification of individuals at high risk of developing cardiomyopathy, even before symptoms occur. These models have the potential to utilise diverse clinical input datasets such as electrocardiogram recordings, cardiac imaging, and other multi-modal genetic and omics datasets. Despite their current underrepresentation in literature, ACM diagnosis and risk prediction are expected to greatly benefit from AI computational capabilities, as has been the case for other cardiomyopathies. As AI-based models improve, larger and more complicated datasets can be combined. These more complex integrated datasets with larger sample sizes will contribute to further pathophysiological insights, better disease recognition, risk prediction, and improved patient outcomes.

Improving the efficiency and accuracy of cardiovascular magnetic resonance with artificial intelligence-review of evidence and proposition of a roadmap to clinical translation

BACKGROUND

Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment of heart disease; however, limitations of CMR include long exam times and high complexity compared to other cardiac imaging modalities. Recently advancements in artificial intelligence (AI) technology have shown great potential to address many CMR limitations. While the developments are remarkable, translation of AI-based methods into real-world CMR clinical practice remains at a nascent stage and much work lies ahead to realize the full potential of AI for CMR.

METHODS

Herein we review recent cutting-edge and representative examples demonstrating how AI can advance CMR in areas such as exam planning, accelerated image reconstruction, post-processing, quality control, classification and diagnosis.

RESULTS

These advances can be applied to speed up and simplify essentially every application including cine, strain, late gadolinium enhancement, parametric mapping, 3D whole heart, flow, perfusion and others. AI is a unique technology based on training models using data. Beyond reviewing the literature, this paper discusses important AI-specific issues in the context of CMR, including (1) properties and characteristics of datasets for training and validation, (2) previously published guidelines for reporting CMR AI research, (3) considerations around clinical deployment, (4) responsibilities of clinicians and the need for multi-disciplinary teams in the development and deployment of AI in CMR, (5) industry considerations, and (6) regulatory perspectives.

CONCLUSIONS

Understanding and consideration of all these factors will contribute to the effective and ethical deployment of AI to improve clinical CMR.

The application of radiology for dilated cardiomyopathy diagnosis, treatment, and prognosis prediction: a bibliometric analysis

Background

Radiology plays a highly crucial role in the diagnosis, treatment, and prognosis prediction of dilated cardiomyopathy (DCM). Related research has increased rapidly over the past few years, but systematic analyses are lacking. This study thus aimed to provide a reference for further research by analyzing the knowledge field, development trends, and research hotspots of radiology in DCM using bibliometric methods.

Methods

Articles on the radiology of DCM published between 2002 and 2021 in the Web of Science Core Collection database (WoSCCd) were searched and analyzed. Data were retrieved and analyzed using CiteSpace V, VOSviewer, and Scimago Graphic software, and included the name, research institution, and nationality of authors; journals of publication; and the number of citations.

Results

A total of 4,257 articles were identified on radiology of DCM from WoSCCd. The number of articles published in this field has grown steadily from 2002 to 2021 and is expected to reach 392 annually by 2024. According to subfields, the number of papers published in cardiac magnetic resonance field increased steadily. The authors from the United States published the most (1,364 articles, 32.04%) articles. The author with the most articles published was Bax JJ (54 articles, 1.27%) from Leiden University Medical Center. The most cited article was titled "2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure", with 138 citations. Citation-based clustering showed that arrhythmogenic cardiomyopathy, T1 mapping, and endomyocardial biopsy are the current hots pots for research in DCM radiology. The most frequently occurring keyword was "dilated cardiomyopathy". The keyword-based clusters mainly included "late gadolinium enhancement", "congestive heart failure", "cardiovascular magnetic resonance", "sudden cardiac death", "ventricular arrhythmia", and "cardiac resynchronization therapy".

Conclusions

The United States and Northern Europe are the most influential countries in research on DCM radiology, with many leading distinguished research institutions. The current research hots pots are myocardial fibrosis, risk stratification of ventricular arrhythmia, the prognosis of cardiac resynchronization therapy (CRT) treatment, and subtype classification of DCM.

Clinical Significance of Action Research-Based Seamless Care to Improve Imaging Efficiency and Patients' Cognition, and Alleviate Patient Anxiety

Objective

The present study was undertaken to assess the clinical significance of action research-based seamless care to improve imaging efficiency and alleviate patient anxiety.

Methods

A total of eighty patients who underwent imaging examinations in our hospital between May 2019 and November 2020 were recruited for this study. The patients were randomly assigned to two groups: the control group receiving routine care and the observation group receiving seamless care based on action research. The random assignment was conducted using a simple random sampling technique, ensuring an equal allocation of participants to each group at a 1:1 ratio, resulting in 40 cases in each group. Outcome measures included imaging examination duration, mean nursing duration, examination cognition, and negative emotion scores.

Results

Seamless care provided shorter imaging examination duration and nursing duration, and better ensured uneventful examinations than routine care (P<0.05). Patients given seamless care exhibited higher examination cognition versus those receiving routine care (P<0.05). Seamless care offered more mitigation of negative emotions for patients than routine care (P<0.05).

Conclusion

Action research-based seamless care effectively improves imaging efficiency and patients' awareness of imaging examinations and contributes to alleviating patients' adverse events.

Real world hospital costs following stress echocardiography in the UK: a costing study from the EVAREST/BSE-NSTEP multi-entre study

BACKGROUND

Stress echocardiography is widely used to detect coronary artery disease, but little evidence on downstream hospital costs in real-world practice is available. We examined how stress echocardiography accuracy and downstream hospital costs vary across NHS hospitals and identified key factors that affect costs to help inform future clinical planning and guidelines.

METHODS

Data on 7636 patients recruited from 31 NHS hospitals within the UK between 2014 and 2020 as part of EVAREST/BSE-NSTEP clinical study, were used. Data included all diagnostic tests, procedures, and hospital admissions for 12 months after a stress echocardiogram and were costed using the NHS national unit costs. A decision tree was built to illustrate the clinical pathway and estimate average downstream hospital costs. Multi-level regression analysis was performed to identify variation in accuracy and costs at both patient, procedural, and hospital level. Linear regression and extrapolation were used to estimate annual hospital cost-savings associated with increasing predictive accuracy at hospital and national level.

RESULTS

Stress echocardiography accuracy varied with patient, hospital and operator characteristics. Hypertension, presence of wall motion abnormalities and higher number of hospital cardiology outpatient attendances annually reduced accuracy, adjusted odds ratio of 0.78 (95% CI 0.65 to 0.93), 0.27 (95% CI 0.15 to 0.48), 0.99 (95% CI 0.98 to 0.99) respectively, whereas a prior myocardial infarction, angiotensin receptor blocker medication, and greater operator experience increased accuracy, adjusted odds ratio of 1.77 (95% CI 1.34 to 2.33), 1.64 (95% CI 1.22 to 2.22), and 1.06 (95% CI 1.02 to 1.09) respectively. Average downstream costs were £646 per patient (SD 1796) with significant variation across hospitals. The average downstream costs between the 31 hospitals varied from £384-1730 per patient. False positive and false negative tests were associated with average downstream costs of £1446 (SD £601) and £4192 (SD 3332) respectively, driven by increased non-elective hospital admissions, adjusted odds ratio 2.48 (95% CI 1.08 to 5.66), 21.06 (95% CI 10.41 to 42.59) respectively. We estimated that an increase in accuracy by 1 percentage point could save the NHS in the UK £3.2 million annually.

CONCLUSION

This study provides real-world evidence of downstream costs associated with stress echocardiography practice in the UK and estimates how improvements in accuracy could impact healthcare expenditure in the NHS. A real-world downstream costing approach could be adopted more widely in evaluation of imaging tests and interventions to reflect actual value for money and support realistic planning.

Echocardiography in the Diagnosis of Cardiomyopathies: Current Status and Future Directions

Cardiomyopathies are a challenging pathology and echocardiography is essential for diagnosis and prognosis. The most frequent cardiomyopathies are the dilated cardiomyopathy (DCM) and the hypertrophic cardiomyopathy (HCM), followed by the less frequent restrictive (RCM) and arrhythmogenic right ventricle cardiomyopathies (ARVC). Echocardiography can identify diagnostic features, and guide further testing for a definitive diagnosis. Echographic parameters are involved in risk score computing and prognosis assessment. While the most prevalent hallmark of HCM is the asymmetric left ventricular hypertrophy and systolic anterior motion of the mitral valve with the obstructive phenotype, DCM shows dilated left ventricle with different degrees of systolic dysfunction, and RCM is usually characterized by undilated ventricles associated with atrial enlargement. The aim of this review is to display and compare the most frequent cardiomyopathies encountered in clinical practice and highlight their most characteristic features in a useful way for the practicing clinician.

Construction of Immune-Related ceRNA Network in Dilated Cardiomyopathy: Based on Sex Differences

Background: Immune targeted therapy has become an attractive therapeutic approach for patients with dilated cardiomyopathy (DCM) recently. Genetic predisposition and gender play a critical role in immune-related responses of DCM. This study aimed to perform a bioinformatics analysis of molecular differences between male and female samples and identify immune-related ceRNA network in DCM.

Methods: The gene expression microarray and clinical features dataset of GSE19303 was downloaded from the GEO. The raw data were preprocessed, followed by identification of differentially expressed genes (DEGs) between male and female DCM samples. Crucial functions and pathway enrichment analysis of DEGs were investigated through GO analysis and KEGG pathway analysis, respectively. A lncRNA–miRNA–mRNA network was constructed and a central module was extracted from the ceRNA network.

Results: Compared with the female group, the male group benefits more from IA/IgG immunotherapy. Male patients of DCM had a significant positive correlation with the abundance of inflammatory cells (B cells, memory B cells, CD8⁺ Tem cells, and NK cells). Sex difference DEGs had a widespread impact on the signaling transduction, transcriptional regulation, and metabolism in DCM. Subsequently, we constructed an immune-related ceRNA network based on sex differences in DCM, including five lncRNAs, six miRNAs, and 29 mRNAs. Furthermore, we extracted a central module from the ceRNA network, including two lncRNAs (XIST and LINC00632), three miRNAs (miR-1-3p, miR-17-5p, and miR-22-3p), and six mRNAs (CBL, CXCL12, ESR1, IGF1R, IL6ST, and STC1). Among these DEGs, CBL, CXCL12, and IL6ST expression was considered to be associated with inflammatory cell infiltration in DCM.

Conclusions: The identified ceRNA network and their enriched pathways may provide genetic insights into the phenotypic diversity of female and male patients with DCM and may provide a basis for development of sex-related individualization of immunotherapy.